Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    names of individuals and specific nouns related to people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    names ending in suffixes like -dale, -ford, -er

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -1.02
     kasarigan
    -0.90
    tagHelperRunner
    -0.87
     CreateTagHelper
    -0.87
    OGND
    -0.84
     Chwiliwch
    -0.81
    AndEndTag
    -0.81
     виправивши
    -0.79
     otomatig
    -0.77
     مرئيه
    -0.76
    POSITIVE LOGITS
     Profesional
    0.45
     located
    0.44
     professional
    0.40
     professionally
    0.39
    -
    0.38
    we
    0.37
    it
    0.37
    store
    0.37
     technology
    0.37
    location
    0.37
    Act Density 0.034%

    No Known Activations